© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3391
    Prev
    Next
    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.60
    harapkan
    -0.56
     Paglinawan
    -0.55
     تانيه
    -0.53
     nég
    -0.48
     linkovi
    -0.48
     Soyez
    -0.47
     incendie
    -0.47
     المعيارى
    -0.46
    ِّف
    -0.46
    POSITIVE LOGITS
    apimachinery
    0.64
    AndEndTag
    0.60
    FieldDescriptor
    0.59
    ity
    0.58
     defaultstate
    0.56
    elemField
    0.55
    opy
    0.54
    sch
    0.54
     Hark
    0.53
    είς
    0.51
    Activations Density 0.000%

    No Known Activations